基于双目视觉的人机交互测距方法研究Research on Human-Computer Interaction Distance Measurement Method Based on Binocular Vision
官世杰
摘要(Abstract):
随着人机交互、无人驾驶等领域的兴起,机器视觉已成为目前重点的研究领域之一.对比研究了红外测距、超声波测距和双目测距三种测距方法,采用计算机视觉技术提出了一种基于双目视觉的人机交互测距方法,并且建立了人脸检测和逻辑回归模型.首先利用双目相机标定工具箱对双目摄像头进行标定;然后将采集到的行人图像导入计算机,对未检测到的图像利用逻辑回归模型给出预测,通过改进的BM算法进行立体匹配获得视差图像;最后通过鼠标点击相应位置进而获得该位置的深度信息,从而实现测距功能.实验结果表明,提出的双目测距方法效率高、结果精确,在1 800~3 600 mm的测距误差可保证在4%以内,具有良好的测距效果.
关键词(KeyWords): 人机交互;双目视觉;人脸检测;改进BM算法;视差图像
基金项目(Foundation): 城市轨道交通车辆系统集成与控制重庆市重点实验室开放基金(CKLURTSIC-KFKT-202006);; 交通工程应用机器人重庆市工程实验室2020年度开放课题(CELTEAR-KFKT-202003)
作者(Author): 官世杰
DOI: 10.16393/j.cnki.37-1436/z.2024.02.010
参考文献(References):
- [1]Zhang Q,Wang Y,Li D,et al.Flexible multifunctional platform based on piezoelectric acoustics for human-machine interaction and environmental perception[J].Microsystems & Nanoengineering,2022,8(1):99.
- [2]Cao Y,Yang Y,Qu X,et al.A Self-Powered Triboelectric Hybrid Coder for Human-Machine Interaction[J].Small Methods,2022,6(3):2101529.
- [3]Sun Q,Wang L,Ren G,et al.Smart band-aid:Multifunctional and wearable electronic device for self-powered motion monitoring and human-machine interaction[J].Nano Energy,2022,92:106840.
- [4]Lin Z,Zhang G,Xiao X,et al.A personalized acoustic interface for wearable human-machine interaction[J].Advanced Functional Materials,2022,32(9):2109430.
- [5]Duan S,Wang B,Lin Y,et al.Waterproof mechanically robust multifunctional conformal sensors for underwater interactive human-machine interfaces[J].Advanced Intelligent Systems,2021,3(9):2100056.
- [6]黄孝慈,舒方林,曹文冠.基于双目视觉的前方车辆测距方法研究[J].汽车技术,2021,555(12):16-21.
- [7]Ren Z,Liao J,Cai L.Three-dimensional measurement of small mechanical parts under a complicated background based on stereo vision[J].Applied optics,2010,49(10):1789-1801.
- [8]Xue T,Qu L,Cao Z,et al.Three-dimensional feature parameters measurement of bubbles in gas–liquid two-phase flow based on virtual stereo vision[J].Flow Measurement and Instrumentation,2012,27:29-36.
- [9]王浩,程进,张春倩,等.电子屏幕智能防近视系统[J].传感器世界,2021,27(11):10-13.
- [10]成慧芳.STM32的智能巡检小车设计[J].电子世界,2021,630(24):63-64.
- [11]许为.六论以用户为中心的设计:智能人机交互的人因工程途径[J].应用心理学,2022,28(03):195-213.
- [12]何森,侯宏录,王尧.标定飞机舵面角位移的双圆靶单目视觉方法[J].兵工学报,2007,124(07):889-892.
- [13]王利华,李亮亮,郭恒林.基于目标的相机标定方法[J].北京测绘,2021,35(03):372-375.
- [14]Karim S,Tong G,Li J,et al.Current advances and future perspectives of image fusion:A comprehensive review[J].Information Fusion,2022,90:185-217.
- [15]林云,雷洋,曾俊俊.抗冲击噪声的核对数最小绝对差算法[J].电子技术应用,2016,42(02):78-80+84.
- [16]Bird B,Wright T,Watson S,et al.Autonomous void detection and characterisation in point clouds and triangular meshes[J].International Journal of Computational Vision and Robotics,2019,9(4):368-386.